Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/escoto/rustifymyclaw/docs-updatenpx skills add Escoto/RustifyMyClaw --skill docs-updategit clone --depth 1 https://github.com/Escoto/RustifyMyClawWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00023 | $0.01351 |
| Opus 5 | $0.00012 | $0.00675 |
| Sonnet 5 | $0.00005 | $0.00270 |
| Haiku 4.5 | $0.00002 | $0.00135 |
Grade A, and why
docs-update scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation structure
Core files (keep lean)
| File | Purpose | Keep it |
|---|---|---|
CLAUDE.md |
Coding rules and "How to Add X" checklists. Read first when coding. | Prescriptive, minimal. Checklist format. |
AGENTS.md |
Quick reference for AI agents. Module table, key patterns, common mistakes. | High-density, no fluff. Max 100 lines. |
Detailed docs (can grow)
| File | Purpose | Detail level |
|---|---|---|
docs/architecture.md |
System design, data flow, component specs, design decisions. | Comprehensive. Diagrams welcome. |
docs/configuration.md |
Full config.yaml field reference with examples. |
Exhaustive. User-facing. |
README.md |
Project intro, quick start, installation. | Marketing + getting started. |
Internal/historical (do not reference in public docs)
desired_architecture.md— planning scratchpad, not authoritativeCONTRIBUTING.md— PR process, branch conventions
Decision tree: What to update?
You changed a trait or added a new component type
Update:
docs/architecture.md— component description, trait signature, extension point sectionCLAUDE.md— "How to Add X" checklist if pattern changed
Keep lean: If the trait is already documented, just update the signature. Don't duplicate examples.
You refactored internal construction (like the resolve_users fix)
Update:
CLAUDE.md— "How to Add X" checklist (steps changed)docs/architecture.md— extension point description, remove outdated patterns (e.g., "two-phase construction")
Do NOT update: AGENTS.md unless the refactor changes a key pattern that appears in the "Common mistakes" or "Key patterns" section.
You added a new config field
Update:
docs/configuration.md— add to field reference table with type, default, descriptionexamples/config.yaml— add example usage if not obvious
Do NOT update: CLAUDE.md or AGENTS.md unless it's a new top-level section.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 138 lines · 23 tokens per session scan A b667b7595da3
docs-update is a skill published in the GitHub repository Escoto/RustifyMyClaw (8 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 23 tokens to every session and 1,351 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
spec-kitty-charter-doctrine
Run charter interview, generation, context, and sync workflows for project governance in Spec Kitty 3.x. Access doctrine artifacts programmatically via DoctrineService. Resolve agent profiles. Load action-scoped governance context iteratively, not all at once. Triggers: "interview for charter", "generate charter"…
debugging-executions
Debug failed or wrong-output workflow executions using executions tools. Load when the user reports execution failures, unexpected node output, empty parameter values after a successful run, or a node showing a red or failed expression error.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
google-gmail-skill
Send, search, and read Gmail emails. Supports composing emails with attachments, searching by query, and reading email content.
frontend-browser-review
Shared workflow for browser-based review of user-visible frontend changes in Langfuse. Use when a change affects UI behavior, layout, styling, navigation, or browser-visible regressions and should be checked with available browser automation before signoff.
vision-skill
Understand images (describe content, answer questions about them, extract text/OCR) via a vision model. Use when the user asks what an image, screenshot, chart, scan, or photo contains.